<ul><li>Handling imbalance in class distribution when building a classifier over tabular data has been a problem of long-standing interest.</li><li>One popular approach is augmenting the training dataset with synthetically generated data.</li><li>State-of-the-art deep generative models yield lower-quality minority examples than majority examples.</li><li>A technique of converting binary class labels to ternary class labels by introducing a class for the overlap region significantly improves the quality of generated data.</li></ul>

Synthetic Tabular Data Generation for Imbalanced Classification: The Surprising Effectiveness of an Overlap Class

Discover more